Engineering notes on AI agents, harness design, and developer tools.
Start a project with a deliberately minimal harness — interactive USER gates, docs-first, no autonomous loop — and graduate to autonomy only after customer evidence (personas, interviews, simulation reports) appears.
Have the hook config file declare only *what events to subscribe to* and route every one of them to a single handler binary; keep all branching, transformation, and policy in that handler.
A single append-only file where an autonomous harness records every task it could not automate, who handled it manually, and the condition under which automation could resume.
No posts match the selected tag.